apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-06-17 15:25:17 +02:00
Code Issues Projects Releases Packages Wiki Activity

tried to tweak the instructions but still can't get the agents to render both results

Browse source
This commit is contained in:
Salman Paracha 2026-01-16 23:34:30 -08:00
parent bbbe627920
commit 74c978cc17
2 changed files with 8 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

9
demos/use_cases/multi_agent_with_crewai_langchain/crewai/flight_agent.py
View file

@ -65,9 +65,7 @@ Your task:
2. Convert technical data into friendly, readable text
3. Use 12-hour time format (e.g., "9:00 AM")
4. Organize flights chronologically by departure time
5. Include terminal/gate info when available
NOTE: Multi-agent context: If the conversation includes information from other sources, incorporate it naturally."""
5. Include terminal/gate info when available6. NOTE (Multi-agent context): If the conversation includes information from other sources that are not flight-related, incorporate it naturally."""
def build_flight_crew(
@ -156,14 +154,15 @@ def build_flight_crew(
backstory=SYSTEM_PROMPT,
tools=[resolve_airport_code_tool, search_flights],
llm=llm,
verbose=False,
verbose=True,
reasoning=False,
)
task = Task(
description=(
"Answer the user's request based on this conversation:\n{conversation}\n\n"
"CRITICAL: Output ONLY your final answer to the user. Do NOT output:\n"
"CRITICAL: NOTE you are part of a multi-agent setup, so if the conversation includes information from other sources that are not flight-related, incorporate it naturally.\n"
"Output ONLY your final answer to the user. Do NOT show:\n"
"- Thought, Action, Action Input, Observation, or any reasoning steps\n"
"- Tool names, parameters, or results\n"
"- Planning or internal deliberation\n\n"

10
demos/use_cases/multi_agent_with_crewai_langchain/langchain/weather_agent.py
View file

@ -29,8 +29,8 @@ logger = logging.getLogger(__name__)
LLM_GATEWAY_ENDPOINT = os.getenv(
"LLM_GATEWAY_ENDPOINT", "http://host.docker.internal:12000/v1"
)
WEATHER_MODEL = "openai/gpt-4o"
LOCATION_MODEL = "openai/gpt-4o-mini"
WEATHER_MODEL = "gpt-4o"
LOCATION_MODEL = "gpt-4o-mini"
openai_client_via_plano = AsyncOpenAI(
base_url=LLM_GATEWAY_ENDPOINT,
@ -250,8 +250,7 @@ class WeatherToolInput(BaseModel):
)
WEATHER_SYSTEM_PROMPT = """
You are a weather assistant in a multi-agent system. You will receive weather data in JSON format with these fields:
WEATHER_SYSTEM_PROMPT = """You are a weather assistant in a multi-agent system. You will receive weather data in JSON format with these fields:
- "location": City name
- "forecast": Array of weather objects, each with date, day_name, temperature_c, temperature_f, temperature_max_c, temperature_min_c, weather_code, sunrise, sunset
@ -264,8 +263,7 @@ WEATHER_SYSTEM_PROMPT = """
4. Include temperature in both Celsius and Fahrenheit
5. Describe conditions naturally based on weather_code
6. Use conversational language
NOTE: Multi-agent context: You are part of a larger system. If the conversation includes additional context or information from other sources, acknowledge and incorporate it naturally into your response. Your primary focus is weather, but be aware of the full conversation context.
7. NOTE (Multi-agent context): If the conversation includes information from other agents and sources incorporate it naturally.
Remember: Only use the provided data. If fields are null, mention data is unavailable."""